So I feel I have made some progress on Nutch
However I am now getting another error which I am having difficulty navigating
through:
bin/nutch inject TestCrawl/crawldb url
produces this below
Do you have to run Cygwin under Admin for it to work?
Injector: Converting injected urls to crawl db entries.
Exception in thread "main" java.lang.UnsatisfiedLinkError:
org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z
at org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Native Method)
at
org.apache.hadoop.io.nativeio.NativeIO$Windows.access(NativeIO.java:570)
at org.apache.hadoop.fs.FileUtil.canRead(FileUtil.java:977)
at
org.apache.hadoop.util.DiskChecker.checkAccessByFileMethods(DiskChecker.java:173)
at
org.apache.hadoop.util.DiskChecker.checkDirAccess(DiskChecker.java:160)
at org.apache.hadoop.util.DiskChecker.checkDir(DiskChecker.java:94)
at
org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.confChanged(LocalDirAllocator.java:285)
at
org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.getLocalPathForWrite(LocalDirAllocator.java:344)
at
org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:150)
at
org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:131)
at
org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:115)
at
org.apache.hadoop.mapred.LocalDistributedCacheManager.setup(LocalDistributedCacheManager.java:131)
at
org.apache.hadoop.mapred.LocalJobRunner$Job.<init>(LocalJobRunner.java:163)
at
org.apache.hadoop.mapred.LocalJobRunner.submitJob(LocalJobRunner.java:731)
at
org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:432)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1285)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1282)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Unknown Source)
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1282)
at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1303)
at org.apache.nutch.crawl.Injector.inject(Injector.java:376)
at org.apache.nutch.crawl.Injector.run(Injector.java:467)
at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:70)
at org.apache.nutch.crawl.Injector.main(Injector.java:441)
